Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework

Guan, Hewen; Yuan, Qihang; Lv, Kejia; Qi, Yushuo; Jiang, Yuankuan; Zhang, Shumeng; Miao, Dong; Wang, Zhiyi; Lin, Jingrong

doi:10.7150/jca.94759



International Journal of Biological Sciences

International Journal of Medical Sciences

Theranostics

Journal of Genomics

Nanotheranostics

Global reach, higher impact

Full Text | PDF

J Cancer 2024; 15(11):3350-3361. doi:10.7150/jca.94759 This issue Cite

Research Paper

Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework

Hewen Guan^1#, Qihang Yuan^2#, Kejia Lv¹, Yushuo Qi¹, Yuankuan Jiang¹, Shumeng Zhang¹, Dong Miao¹, Zhiyi Wang¹, Jingrong Lin^1✉

1. Department of Dermatology, First Affiliated Hospital of Dalian Medical University, Dalian, Liaoning, China.
2. Department of General Surgery, First Affiliated Hospital of Dalian Medical University, Dalian, Liaoning, China.
# Hewen Guan, Qihang Yuan contributed to this article equally.

Citation:

Guan H, Yuan Q, Lv K, Qi Y, Jiang Y, Zhang S, Miao D, Wang Z, Lin J. Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework. J Cancer 2024; 15(11):3350-3361. doi:10.7150/jca.94759. https://www.jcancer.org/v15p3350.htm

Other styles

Abstract

This study has used machine learning algorithms to develop a predictive model for differentiating between dermoscopic images of basal cell carcinoma (BCC) and actinic keratosis (AK). We compiled a total of 904 dermoscopic images from two sources — the public dataset (HAM10000) and our proprietary dataset from the First Affiliated Hospital of Dalian Medical University (DAYISET 1) — and subsequently categorised these images into four distinct cohorts. The study developed a deep learning model for quantitative analysis of image features and integrated 15 machine learning algorithms, generating 207 algorithmic combinations through random combinations and cross-validation. The final predictive model, formed by integrating XGBoost with Lasso regression, exhibited effective performance in the differential diagnosis of BCC and AK. The model demonstrated high sensitivity in the training set and maintained stable performance in three validation sets. The area under the curve (AUC) value reached 1.000 in the training set and an average of 0.695 in the validation sets. The study concludes that the constructed discriminative diagnostic model based on machine learning algorithms has excellent predictive capabilities that could enhance clinical decision-making efficiency, reduce unnecessary biopsies, and provide valuable guidance for further treatment.

Keywords: machine learning, basal cell carcinoma, actinic keratosis, dermoscopy, artificial intelligence

Citation styles

APA

Guan, H., Yuan, Q., Lv, K., Qi, Y., Jiang, Y., Zhang, S., Miao, D., Wang, Z., Lin, J. (2024). Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework. Journal of Cancer, 15(11), 3350-3361. https://doi.org/10.7150/jca.94759.

ACS

Guan, H.; Yuan, Q.; Lv, K.; Qi, Y.; Jiang, Y.; Zhang, S.; Miao, D.; Wang, Z.; Lin, J. Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework. J. Cancer 2024, 15 (11), 3350-3361. DOI: 10.7150/jca.94759.

NLM

CSE

Guan H, Yuan Q, Lv K, Qi Y, Jiang Y, Zhang S, Miao D, Wang Z, Lin J. 2024. Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework. J Cancer. 15(11):3350-3361.

This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/). See http://ivyspring.com/terms for full terms and conditions.